Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 27954
    Prev
    Next
    INDEX
    Explanations

    expressions of feelings of neglect or abandonment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mini
    -0.15
    ogh
    -0.14
    dney
    -0.14
     Svens
    -0.14
    vida
    -0.14
    ÏĢοÏĤ
    -0.13
     moons
    -0.13
    ãĥĨãĥ«
    -0.13
    ansi
    -0.13
    墨
    -0.13
    POSITIVE LOGITS
     alone
    0.52
     Alone
    0.42
    alone
    0.40
    -alone
    0.36
     lone
    0.34
     AL
    0.33
     solo
    0.31
    _al
    0.30
    Al
    0.30
     along
    0.29
    Activations Density 0.027%

    No Known Activations